aboutsummaryrefslogtreecommitdiffstats
path: root/arch/arm/kernel/perf_event_v6.c
diff options
context:
space:
mode:
Diffstat (limited to '')
-rw-r--r--arch/arm/kernel/perf_event_v6.c307
1 files changed, 79 insertions, 228 deletions
diff --git a/arch/arm/kernel/perf_event_v6.c b/arch/arm/kernel/perf_event_v6.c
index 03664b0e8fa4..abfeb04f3213 100644
--- a/arch/arm/kernel/perf_event_v6.c
+++ b/arch/arm/kernel/perf_event_v6.c
@@ -65,13 +65,11 @@ enum armv6_counters {
* accesses/misses in hardware.
*/
static const unsigned armv6_perf_map[PERF_COUNT_HW_MAX] = {
+ PERF_MAP_ALL_UNSUPPORTED,
[PERF_COUNT_HW_CPU_CYCLES] = ARMV6_PERFCTR_CPU_CYCLES,
[PERF_COUNT_HW_INSTRUCTIONS] = ARMV6_PERFCTR_INSTR_EXEC,
- [PERF_COUNT_HW_CACHE_REFERENCES] = HW_OP_UNSUPPORTED,
- [PERF_COUNT_HW_CACHE_MISSES] = HW_OP_UNSUPPORTED,
[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = ARMV6_PERFCTR_BR_EXEC,
[PERF_COUNT_HW_BRANCH_MISSES] = ARMV6_PERFCTR_BR_MISPREDICT,
- [PERF_COUNT_HW_BUS_CYCLES] = HW_OP_UNSUPPORTED,
[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = ARMV6_PERFCTR_IBUF_STALL,
[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = ARMV6_PERFCTR_LSU_FULL_STALL,
};
@@ -79,116 +77,31 @@ static const unsigned armv6_perf_map[PERF_COUNT_HW_MAX] = {
static const unsigned armv6_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
[PERF_COUNT_HW_CACHE_OP_MAX]
[PERF_COUNT_HW_CACHE_RESULT_MAX] = {
- [C(L1D)] = {
- /*
- * The performance counters don't differentiate between read
- * and write accesses/misses so this isn't strictly correct,
- * but it's the best we can do. Writes and reads get
- * combined.
- */
- [C(OP_READ)] = {
- [C(RESULT_ACCESS)] = ARMV6_PERFCTR_DCACHE_ACCESS,
- [C(RESULT_MISS)] = ARMV6_PERFCTR_DCACHE_MISS,
- },
- [C(OP_WRITE)] = {
- [C(RESULT_ACCESS)] = ARMV6_PERFCTR_DCACHE_ACCESS,
- [C(RESULT_MISS)] = ARMV6_PERFCTR_DCACHE_MISS,
- },
- [C(OP_PREFETCH)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- },
- [C(L1I)] = {
- [C(OP_READ)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = ARMV6_PERFCTR_ICACHE_MISS,
- },
- [C(OP_WRITE)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- [C(OP_PREFETCH)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- },
- [C(LL)] = {
- [C(OP_READ)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- [C(OP_WRITE)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- [C(OP_PREFETCH)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- },
- [C(DTLB)] = {
- /*
- * The ARM performance counters can count micro DTLB misses,
- * micro ITLB misses and main TLB misses. There isn't an event
- * for TLB misses, so use the micro misses here and if users
- * want the main TLB misses they can use a raw counter.
- */
- [C(OP_READ)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = ARMV6_PERFCTR_DTLB_MISS,
- },
- [C(OP_WRITE)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = ARMV6_PERFCTR_DTLB_MISS,
- },
- [C(OP_PREFETCH)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- },
- [C(ITLB)] = {
- [C(OP_READ)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = ARMV6_PERFCTR_ITLB_MISS,
- },
- [C(OP_WRITE)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = ARMV6_PERFCTR_ITLB_MISS,
- },
- [C(OP_PREFETCH)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- },
- [C(BPU)] = {
- [C(OP_READ)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- [C(OP_WRITE)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- [C(OP_PREFETCH)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- },
- [C(NODE)] = {
- [C(OP_READ)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- [C(OP_WRITE)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- [C(OP_PREFETCH)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- },
+ PERF_CACHE_MAP_ALL_UNSUPPORTED,
+
+ /*
+ * The performance counters don't differentiate between read and write
+ * accesses/misses so this isn't strictly correct, but it's the best we
+ * can do. Writes and reads get combined.
+ */
+ [C(L1D)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV6_PERFCTR_DCACHE_ACCESS,
+ [C(L1D)][C(OP_READ)][C(RESULT_MISS)] = ARMV6_PERFCTR_DCACHE_MISS,
+ [C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV6_PERFCTR_DCACHE_ACCESS,
+ [C(L1D)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV6_PERFCTR_DCACHE_MISS,
+
+ [C(L1I)][C(OP_READ)][C(RESULT_MISS)] = ARMV6_PERFCTR_ICACHE_MISS,
+
+ /*
+ * The ARM performance counters can count micro DTLB misses, micro ITLB
+ * misses and main TLB misses. There isn't an event for TLB misses, so
+ * use the micro misses here and if users want the main TLB misses they
+ * can use a raw counter.
+ */
+ [C(DTLB)][C(OP_READ)][C(RESULT_MISS)] = ARMV6_PERFCTR_DTLB_MISS,
+ [C(DTLB)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV6_PERFCTR_DTLB_MISS,
+
+ [C(ITLB)][C(OP_READ)][C(RESULT_MISS)] = ARMV6_PERFCTR_ITLB_MISS,
+ [C(ITLB)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV6_PERFCTR_ITLB_MISS,
};
enum armv6mpcore_perf_types {
@@ -220,13 +133,11 @@ enum armv6mpcore_perf_types {
* accesses/misses in hardware.
*/
static const unsigned armv6mpcore_perf_map[PERF_COUNT_HW_MAX] = {
+ PERF_MAP_ALL_UNSUPPORTED,
[PERF_COUNT_HW_CPU_CYCLES] = ARMV6MPCORE_PERFCTR_CPU_CYCLES,
[PERF_COUNT_HW_INSTRUCTIONS] = ARMV6MPCORE_PERFCTR_INSTR_EXEC,
- [PERF_COUNT_HW_CACHE_REFERENCES] = HW_OP_UNSUPPORTED,
- [PERF_COUNT_HW_CACHE_MISSES] = HW_OP_UNSUPPORTED,
[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = ARMV6MPCORE_PERFCTR_BR_EXEC,
[PERF_COUNT_HW_BRANCH_MISSES] = ARMV6MPCORE_PERFCTR_BR_MISPREDICT,
- [PERF_COUNT_HW_BUS_CYCLES] = HW_OP_UNSUPPORTED,
[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = ARMV6MPCORE_PERFCTR_IBUF_STALL,
[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = ARMV6MPCORE_PERFCTR_LSU_FULL_STALL,
};
@@ -234,114 +145,26 @@ static const unsigned armv6mpcore_perf_map[PERF_COUNT_HW_MAX] = {
static const unsigned armv6mpcore_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
[PERF_COUNT_HW_CACHE_OP_MAX]
[PERF_COUNT_HW_CACHE_RESULT_MAX] = {
- [C(L1D)] = {
- [C(OP_READ)] = {
- [C(RESULT_ACCESS)] =
- ARMV6MPCORE_PERFCTR_DCACHE_RDACCESS,
- [C(RESULT_MISS)] =
- ARMV6MPCORE_PERFCTR_DCACHE_RDMISS,
- },
- [C(OP_WRITE)] = {
- [C(RESULT_ACCESS)] =
- ARMV6MPCORE_PERFCTR_DCACHE_WRACCESS,
- [C(RESULT_MISS)] =
- ARMV6MPCORE_PERFCTR_DCACHE_WRMISS,
- },
- [C(OP_PREFETCH)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- },
- [C(L1I)] = {
- [C(OP_READ)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = ARMV6MPCORE_PERFCTR_ICACHE_MISS,
- },
- [C(OP_WRITE)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- [C(OP_PREFETCH)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- },
- [C(LL)] = {
- [C(OP_READ)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- [C(OP_WRITE)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- [C(OP_PREFETCH)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- },
- [C(DTLB)] = {
- /*
- * The ARM performance counters can count micro DTLB misses,
- * micro ITLB misses and main TLB misses. There isn't an event
- * for TLB misses, so use the micro misses here and if users
- * want the main TLB misses they can use a raw counter.
- */
- [C(OP_READ)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = ARMV6MPCORE_PERFCTR_DTLB_MISS,
- },
- [C(OP_WRITE)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = ARMV6MPCORE_PERFCTR_DTLB_MISS,
- },
- [C(OP_PREFETCH)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- },
- [C(ITLB)] = {
- [C(OP_READ)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = ARMV6MPCORE_PERFCTR_ITLB_MISS,
- },
- [C(OP_WRITE)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = ARMV6MPCORE_PERFCTR_ITLB_MISS,
- },
- [C(OP_PREFETCH)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- },
- [C(BPU)] = {
- [C(OP_READ)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- [C(OP_WRITE)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- [C(OP_PREFETCH)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- },
- [C(NODE)] = {
- [C(OP_READ)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- [C(OP_WRITE)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- [C(OP_PREFETCH)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- },
+ PERF_CACHE_MAP_ALL_UNSUPPORTED,
+
+ [C(L1D)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV6MPCORE_PERFCTR_DCACHE_RDACCESS,
+ [C(L1D)][C(OP_READ)][C(RESULT_MISS)] = ARMV6MPCORE_PERFCTR_DCACHE_RDMISS,
+ [C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV6MPCORE_PERFCTR_DCACHE_WRACCESS,
+ [C(L1D)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV6MPCORE_PERFCTR_DCACHE_WRMISS,
+
+ [C(L1I)][C(OP_READ)][C(RESULT_MISS)] = ARMV6MPCORE_PERFCTR_ICACHE_MISS,
+
+ /*
+ * The ARM performance counters can count micro DTLB misses, micro ITLB
+ * misses and main TLB misses. There isn't an event for TLB misses, so
+ * use the micro misses here and if users want the main TLB misses they
+ * can use a raw counter.
+ */
+ [C(DTLB)][C(OP_READ)][C(RESULT_MISS)] = ARMV6MPCORE_PERFCTR_DTLB_MISS,
+ [C(DTLB)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV6MPCORE_PERFCTR_DTLB_MISS,
+
+ [C(ITLB)][C(OP_READ)][C(RESULT_MISS)] = ARMV6MPCORE_PERFCTR_ITLB_MISS,
+ [C(ITLB)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV6MPCORE_PERFCTR_ITLB_MISS,
};
static inline unsigned long
@@ -653,9 +476,8 @@ static int armv6_map_event(struct perf_event *event)
&armv6_perf_cache_map, 0xFF);
}
-static int armv6pmu_init(struct arm_pmu *cpu_pmu)
+static void armv6pmu_init(struct arm_pmu *cpu_pmu)
{
- cpu_pmu->name = "v6";
cpu_pmu->handle_irq = armv6pmu_handle_irq;
cpu_pmu->enable = armv6pmu_enable_event;
cpu_pmu->disable = armv6pmu_disable_event;
@@ -667,7 +489,26 @@ static int armv6pmu_init(struct arm_pmu *cpu_pmu)
cpu_pmu->map_event = armv6_map_event;
cpu_pmu->num_events = 3;
cpu_pmu->max_period = (1LLU << 32) - 1;
+}
+
+static int armv6_1136_pmu_init(struct arm_pmu *cpu_pmu)
+{
+ armv6pmu_init(cpu_pmu);
+ cpu_pmu->name = "armv6_1136";
+ return 0;
+}
+static int armv6_1156_pmu_init(struct arm_pmu *cpu_pmu)
+{
+ armv6pmu_init(cpu_pmu);
+ cpu_pmu->name = "armv6_1156";
+ return 0;
+}
+
+static int armv6_1176_pmu_init(struct arm_pmu *cpu_pmu)
+{
+ armv6pmu_init(cpu_pmu);
+ cpu_pmu->name = "armv6_1176";
return 0;
}
@@ -687,7 +528,7 @@ static int armv6mpcore_map_event(struct perf_event *event)
static int armv6mpcore_pmu_init(struct arm_pmu *cpu_pmu)
{
- cpu_pmu->name = "v6mpcore";
+ cpu_pmu->name = "armv6_11mpcore";
cpu_pmu->handle_irq = armv6pmu_handle_irq;
cpu_pmu->enable = armv6pmu_enable_event;
cpu_pmu->disable = armv6mpcore_pmu_disable_event;
@@ -703,7 +544,17 @@ static int armv6mpcore_pmu_init(struct arm_pmu *cpu_pmu)
return 0;
}
#else
-static int armv6pmu_init(struct arm_pmu *cpu_pmu)
+static int armv6_1136_pmu_init(struct arm_pmu *cpu_pmu)
+{
+ return -ENODEV;
+}
+
+static int armv6_1156_pmu_init(struct arm_pmu *cpu_pmu)
+{
+ return -ENODEV;
+}
+
+static int armv6_1176_pmu_init(struct arm_pmu *cpu_pmu)
{
return -ENODEV;
}
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.